{"id":1899439,"url":"https://alion.io/job/moveworks-senior-research-scientist-agent-evaluation","title":"Senior Research Scientist - Agent Evaluation","company":{"id":840,"name":"Moveworks","domain":"moveworks.com","url":"https://alion.io/company/moveworks","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Hyderabad, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":22000,"max_usd":46000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":38},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Context Engineering","optional":false},{"name":"Function Calling","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"Structured Outputs","optional":false},{"name":"Claude Code","optional":true},{"name":"Windsurf","optional":true}],"status":"live","first_seen_at":"2026-10-05T10:04:21Z","employer_posted_date":null,"last_verified_at":"2026-10-05T10:04:21Z","board_verified":false,"closed_at":null,"days_open":18,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":18},"description":"We build the evaluation layer that validates AI agents before they reach customers and an automated system that scores across large volumes of agent traces. You'll own core parts of that platform: the pipeline that runs traces through model-based judges at scale and the scoring logic that turns raw output into results teams can act on.\nResponsibilities:\nDesign evaluation methodologies and benchmarks for agent reasoning, planning, tool use, reliability, and safety across LLM-as-a-Judge, trajectory-based, and human evaluation.\nTake problems from research question to prototype to shipped feature, owning them end to end.\nBuild and harden the pipelines and scoring logic behind customer-facing evaluation.\nCurate synthetic and real-world datasets; measure the evaluator itself for consistency and agreement with human labels.\nRequirements:\n5+ years in ML, applied AI, prompt engineering, and agentic AI, including shipping something real to users.\nStrong Python skills.\nPractical depth in agentic AI and context engineering: planning, reasoning, memory, tool use, retrieval, long-context.\nExperience designing evaluation methodologies, not just running evaluations.\nHands-on production work with LLM APIs, prompt engineering, structured output, and cost and latency trade-offs.\nClear communication with technical and non-technical audiences.\nGood to have: experience with AI-assisted development tools (Claude Code, Windsurf, or similar).","description_format":"text","description_chars":1441,"description_truncated":false,"requirements":{"experience_years_min":5,"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":["IT Service & Asset Management","Conversational AI","AI Agents"],"lifecycle":[{"event":"open","at":"2026-10-05T10:04:21Z"}],"visa":[],"liveness":{"score":62,"band":"ok","label":"Likely open","p_open":0.85,"p_active":0.813,"p_room":0.9,"age_days":17,"expected_fill_days":27,"reasons":["seen:17","velocity","win:mid"],"computed_at":"2026-10-23T05:54:15Z"},"pay":null,"html_url":"https://alion.io/job/moveworks-senior-research-scientist-agent-evaluation","json_url":"https://alion.io/job/moveworks-senior-research-scientist-agent-evaluation.json","meta":{"generated_at":"2026-10-23T17:18:09Z","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":26299,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-24T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"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":840},"rest":"https://alion.io/mcp/rest/get_company?id=840"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fmoveworks-senior-research-scientist-agent-evaluation"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"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%2Fmoveworks-senior-research-scientist-agent-evaluation"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"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%2Fmoveworks-senior-research-scientist-agent-evaluation"},{"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/moveworks-senior-research-scientist-agent-evaluation\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fmoveworks-senior-research-scientist-agent-evaluation"}]}