{"id":4783936,"url":"https://alion.io/job/collision-ai-rl-infrastructure-engineer","title":"RL Infrastructure Engineer","company":{"id":6928029,"name":"Collision AI","domain":"collision.ai","url":"https://alion.io/company/collision-2","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":null},"role":"DevOps","role_family":"DevOps","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CUDA","optional":false},{"name":"FSDP","optional":false},{"name":"LLM","optional":false},{"name":"NCCL","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reward Modeling","optional":false},{"name":"SGLang","optional":false},{"name":"Triton","optional":false},{"name":"vLLM","optional":false}],"status":"live","first_seen_at":"2026-11-12T00:31:03Z","employer_posted_date":"2026-11-12","last_verified_at":"2026-11-22T10:44:11Z","board_verified":true,"closed_at":null,"days_open":10,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":10},"description":"Job description\nCollision AI is building models and agents for cyber defense. You’ll develop the infrastructure that trains them through reinforcement learning, helping researchers move from initial experiments to efficient, reliable runs across many GPUs.\nThe role combines systems engineering with a practical understanding of RL. Infrastructure problems can change learning behavior: delayed weight updates, differences between trainer and inference log probabilities, or off-policy drift can resemble problems with the training method itself. You’ll work closely with researchers to understand these interactions and improve performance without compromising training correctness.\nWhat you’ll work on\nTraining and rollout systems. Coordinate trainers, rollout workers, environment execution, and reward computation across GPU clusters. Integrate SGLang for high-throughput sampling, improve trainer-to-inference weight synchronization, and support asynchronous rollouts and off-policy training.\n\nPerformance at scale. Improve distributed training through FSDP, tensor and pipeline parallelism, and efficient NCCL communication. Profile bottlenecks across compute, memory, and networking, and make targeted runtime or CUDA/Triton kernel improvements where they meaningfully improve training efficiency.\n\nTraining correctness and reliability. Develop monitoring and diagnostics that catch stale weights, trainer-inference log-probability mismatches, and off-policy drift during long runs. Build reproducible debugging workflows and recovery mechanisms, and use controlled comparisons to understand how infrastructure changes affect learning.\n\nRequired qualifications\nStrong Python and PyTorch skills, with experience building distributed training or inference infrastructure.\n\nPractical understanding of LLM reinforcement learning, including rollout policies, reward computation, and policy updates.\n\nExperience profiling GPU workloads and resolving performance, correctness, or reliability issues in complex ML systems.\n\nAbility to investigate problems across research and infrastructure code and validate changes on real training runs.\n\nBonus qualifications\nExperience developing RL training pipelines, particularly asynchronous or off-policy systems.\n\nWork on agent environments, sandboxed execution, reward models, or verification pipelines.\n\nExperience extending SGLang, vLLM, or comparable inference runtimes.\n\nExperience with FSDP, tensor or pipeline parallelism, NCCL, CUDA, or Triton.","description_format":"text","description_chars":2494,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Cybersecurity","Information Security"],"lifecycle":[{"event":"open","at":"2026-11-22T07:54:44Z"}],"visa":[],"liveness":{"score":75,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.838,"p_room":0.9,"age_days":10,"expected_fill_days":27,"reasons":["conf:0","win:mid"],"computed_at":"2026-11-22T10:47:43Z"},"pay":null,"html_url":"https://alion.io/job/collision-ai-rl-infrastructure-engineer","json_url":"https://alion.io/job/collision-ai-rl-infrastructure-engineer.json","meta":{"generated_at":"2026-11-22T10:47:43Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":17247,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-23T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":6928029},"rest":"https://alion.io/mcp/rest/get_company?id=6928029"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcollision-ai-rl-infrastructure-engineer"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"free","price":{"credits":0,"usd":0},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fcollision-ai-rl-infrastructure-engineer"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fcollision-ai-rl-infrastructure-engineer"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/collision-ai-rl-infrastructure-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcollision-ai-rl-infrastructure-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":4783936}},{"tool":"search_jobs","arguments":{"company":"collision.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":4783936},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}