Microsoft Logo

Microsoft

Research Intern - Coding Agents & Post-Training Optimization

Posted 8 Days Ago
Be an Early Applicant
In-Office
Redmond, WA, USA
7K-15K Annually
Internship
In-Office
Redmond, WA, USA
7K-15K Annually
Internship
Conduct end-to-end research on improving coding agents through reinforcement learning, fine-tuning, distillation, compression, and inference optimization. Build experiments, evaluate agentic coding models on realistic benchmarks, collaborate with researchers and engineers, present findings, and contribute toward publications or product integrations. The role focuses on making coding agents more reliable, efficient, and affordable at scale.
The summary above was generated by AI
Overview

Research Internships at Microsoft provide a dynamic environment for research careers with a network of world-class research labs led by globally-recognized scientists and engineers, who pursue innovation in a range of scientific and technical disciplines to help solve complex challenges in diverse fields, including computing, healthcare, economics, and the environment. 


We are hiring a Research Intern to make coding agents better, cheaper and faster through post-training: reinforcement learning, fine-tuning, distillation, compression and inference optimization.


Coding agents now plan, edit repositories, run tests and fix failures over long, multi-step trajectories. Making them reliable and affordable is a post-training problem as much as a modeling one. Our team trains, evaluates and ships agentic coding models that power developer tools at scale.


As a Research Intern, you will own a research question end to end; form a hypothesis, build the experiment, measure it on realistic agent benchmarks, and push results toward a paper or a product integration. You will work with researchers and engineers across model training, agent infrastructure and hardware acceleration.


Responsibilities

Research Interns put inquiry and theory into practice. Alongside fellow doctoral candidates and some of the world’s best researchers, Research Interns learn, collaborate, and network for life. Research Interns not only advance their own careers, but they also contribute to exciting research and development strides. During the 12-week internship, Research Interns are paired with mentors and expected to collaborate with other Research Interns and researchers, present findings, and contribute to the vibrant life of the community. Research internships are available in all areas of research, and are offered year-round, though they typically begin in the summer.


Qualifications

Required Qualifications

  • Currently enrolled full time in a Doctoral Degree program in area in Computer Science, Computer Engineering, Electrical Engineering, or a related STEM field.

Other Requirements

  • Research Interns are expected to be physically located in their manager’s Microsoft worksite location for the duration of their internship.
  • In addition to the qualifications below, you’ll need to submit a minimum of two reference letters for this position as well as a cover letter and any relevant work or research samples. After you submit your application, a request for letters may be sent to your list of references on your behalf. Note that reference letters cannot be requested until after you have submitted your application, and furthermore, that they might not be automatically requested for all candidates. You may wish to alert your letter writers in advance, so they will be ready to submit your letter. 

Preferred Qualifications

  • At least one additional quarter/semester of school remaining following the completion of the internship.
  • Research experience in at least one of: LLM post-training (RL, SFT, preference optimization), model compression, or efficient inference.
  • Proficient Python and PyTorch skills, with hands-on experience training or fine-tuning transformer models
  • First-author publications at top venues (NeurIPS, ICML, ICLR, ACL, EMNLP, MLSys, ICSE, FSE) or equivalent research impact.
  • Experience with RL for LLMs at scale using frameworks such as TRL, verl, OpenRLHF or DeepSpeed-Chat.
  • Experience building or training code-generation models or coding agents, and with benchmarks such as SWE-bench, LiveCodeBench, Terminal-Bench or HumanEval.
  • Hands-on work with quantization, distillation, pruning or speculative decoding; familiarity with serving stacks such as vLLM, SGLang, TensorRT-LLM or ONNX Runtime.
  • Familiarity with distributed training (FSDP, DeepSpeed, Megatron) and GPU profiling or kernel work (CUDA, Triton).
  • Clear communication, self-direction, curiosity, and a bias toward hands-on experimentation.
  • Experience collaborating across teams, disciplines and cultures.


The base pay range for this internship is USD $6,810 - $13,480 per month. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $8,920 - $14,610 per month.


Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here: https://careers.microsoft.com/us/en/us-intern-pay


Microsoft accepts applications and processes offers for these roles on an ongoing basis throughout the academic calendar (September - April).


This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled.



Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations.

HQ

Microsoft Redmond, Washington, USA Office

1 Microsoft Way, Redmond, WA, United States, 98052

Microsoft Bellevue, Washington, USA Office

Bellevue, United States

Microsoft Issaquah, Washington, USA Office

Issaquah, United States

Microsoft Kirkland, Washington, USA Office

Kirkland, United States

Microsoft Mercer Island, Washington, USA Office

Mercer Island, United States

Microsoft Sammamish, Washington, USA Office

Sammamish, United States

Microsoft Seattle, Washington, USA Office

Seattle, United States

Similar Jobs

38 Minutes Ago
In-Office
Bellevue, WA, USA
157K-210K Annually
Senior level
157K-210K Annually
Senior level
Cloud • Information Technology • Machine Learning
Develops and manages Primavera P6 master construction schedules for hyperscale data center projects. Coordinates with construction, engineering, operations, and trade teams; conducts schedule risk, critical path, and progress reviews; validates contractor performance through site visits; produces forecasts and reports; and develops recovery plans, corrective actions, and what-if scenarios for project leadership and stakeholders.
Top Skills: MS OfficeMicrosoft ProjectPrimavera P6Smartsheet
46 Minutes Ago
Hybrid
Seattle, WA, USA
131K-181K Annually
Senior level
131K-181K Annually
Senior level
Artificial Intelligence • Cloud • Mobile • Security • Software
Own and grow a portfolio of strategic enterprise customers across North America. Drive adoption, measurable customer value, retention, renewals, and expansion through account planning, executive engagement, cross-functional coordination, technical delivery, incident resolution, and customer advocacy. Manage complex procurement cycles, monitor account health, develop recovery plans, and partner with Sales, Product, Engineering, and Support to achieve customer and commercial outcomes.
Top Skills: APIsCatalystChurnzeroGainsightIntegrationsSaaSSalesforceTotangoVitally
An Hour Ago
Hybrid
Seattle, WA, USA
77K-202K Annually
Senior level
77K-202K Annually
Senior level
Artificial Intelligence • Professional Services • Business Intelligence • Consulting • Cybersecurity • Generative AI
Designs and develops Azure-based generative AI solutions, including conversational applications, retrieval-augmented generation pipelines, agent workflows, cloud-native microservices, and LLM evaluation systems. The role uses Python, Azure AI Services, Azure OpenAI, LangGraph, vector databases, and DevOps practices to deploy and maintain client solutions. Responsibilities also include managing workstreams, communicating technical tradeoffs, reviewing deliverables, mentoring junior colleagues, and collaborating with clients.
Top Skills: Azure Ai ServicesAzure Api ManagementAzure Kubernetes ServiceAzure Openai ServiceC#Claude CodeDevOpsEnterprise Service BusesGithub CopilotJavaScriptLangchainLanggraphLarge Language Model ApisLlmopsAzureModel Context ProtocolPythonVector Databases

What you need to know about the Seattle Tech Scene

Home to tech titans like Microsoft and Amazon, Seattle punches far above its weight in innovation. But its surrounding mountains, sprinkled with world-famous hiking trails and climbing routes, make the city a destination for outdoorsy types as well. Established as a logging town before shifting to shipbuilding and logistics, the Emerald City is now known for its contributions to aerospace, software, biotech and cloud computing. And its status as a thriving tech ecosystem is attracting out-of-town companies looking to establish new tech and engineering hubs.

Key Facts About Seattle Tech

  • Number of Tech Workers: 287,000; 13% of overall workforce (2024 CompTIA survey)
  • Major Tech Employers: Amazon, Microsoft, Meta, Google
  • Key Industries: Artificial intelligence, cloud computing, software, biotechnology, game development
  • Funding Landscape: $3.1 billion in venture capital funding in 2024 (Pitchbook)
  • Notable Investors: Madrona, Fuse, Tola, Maveron
  • Research Centers and Universities: University of Washington, Seattle University, Seattle Pacific University, Allen Institute for Brain Science, Bill & Melinda Gates Foundation, Seattle Children’s Research Institute

Sign up now Access later

Create Free Account

Please log in or sign up to report this job.

Create Free Account