{"id":3762541,"url":"https://alion.io/job/clera-research-engineer-synthetic-data-12","title":"Research Engineer, Synthetic Data","company":{"id":2706,"name":"Clera","domain":"getclera.com","url":"https://alion.io/company/clera","size_band":"11-50","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":80,"open_postings":39,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":6,"computed_at":"2026-11-09T06:03:00Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"junior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Singapore"],"countries":["SG"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":100000,"max":170000,"currency":"USD","period":"year","gross":null,"usd_annual":170000},"salary_estimate":null,"experience_years_min":2,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Docker","optional":false},{"name":"Linux","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false},{"name":"Post-training","optional":false},{"name":"Python","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Synthetic Data","optional":false}],"status":"live","first_seen_at":"2026-11-04T17:26:03Z","employer_posted_date":"2026-11-04","last_verified_at":"2026-11-09T19:42:01Z","board_verified":true,"closed_at":null,"days_open":5,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":5},"description":"About the Role\nJoin a small engineering team building synthetic data systems for AI agents. You will turn real-world professional workflows into scalable training tasks, helping improve how models learn and perform across practical domains.\nWhat You'll Do\nBuild pipelines that transform domain-specific workflows into realistic, structured synthetic training tasks.\n\nWork with subject-matter experts to create tasks for AI agents across professional and technical domains.\n\nDesign generation methods that produce diverse, realistic, and learnable tasks.\n\nDevelop tools to mutate, validate, and improve synthetic tasks.\n\nAnalyze model and agent performance to understand task strengths, limitations, and failure modes.\n\nCreate metrics for task diversity, realism, learnability, and overall quality.\n\nWhat We're Looking For\nTwo or more years of relevant experience in software engineering, machine learning engineering, or AI research, with a technical background.\n\nHands-on experience applying synthetic data methods and delivering end-to-end data generation pipelines for AI or machine learning applications.\n\nProficiency in Python and experience working in Linux environments with containerization tools such as Docker.\n\nExperience with synthetic data quality criteria, evaluation metrics, and the limitations of synthetic data.\n\nBackground building or maintaining evaluation frameworks, benchmarks, or testing environments for AI agents or large language models.\n\nExperience automating the generation, validation, mutation, or processing of structured datasets at scale.\n\nAbility to independently deliver technical projects in loosely defined problem spaces, with care for edge cases and data quality.\n\nFamiliarity with reinforcement learning, agent workflows, or LLM post-training is useful.\n\nCompensation & Benefits\nBase salary range: $100,000 to $170,000 USD annually. Visa sponsorship is available.\nLocation\nOn-site in Singapore, Singapore.","description_format":"text","description_chars":1946,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"Singapore","iso":"SG","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-11-04T19:02:59Z"}],"visa":[{"country":"SG","licensed_sponsor":false,"adverts_offering_sponsorship_24m":6,"sanctioned_now":false,"evidence":"Offered visa sponsorship in 6 of its adverts here in 24 months","filings_12m":null,"filings_prev_12m":null,"green_card_filings_12m":null,"median_offered_wage_usd":null,"route":null,"cap_exempt":false,"checked_at":"2026-11-09T07:32:21+00:00","sources":["Alion: sponsorship offered in the employer's own job adverts (24 months)"],"filings_for_role_12m":0}],"liveness":{"score":24,"band":"cold","label":"Long shot","p_open":1,"p_active":0.321,"p_room":0.75,"age_days":4,"expected_fill_days":6,"reasons":["conf:0","agency","stale_co","velocity","win:late","comp:junior,brand"],"computed_at":"2026-11-09T06:03:00Z"},"pay":{"stated_usd_annual":170000,"is_top_pay":false},"html_url":"https://alion.io/job/clera-research-engineer-synthetic-data-12","json_url":"https://alion.io/job/clera-research-engineer-synthetic-data-12.json","meta":{"generated_at":"2026-11-09T21:39:11Z","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":10257,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-10T00:00:00Z"}},"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":2706},"rest":"https://alion.io/mcp/rest/get_company?id=2706"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fclera-research-engineer-synthetic-data-12"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":2,"usd":0.2},"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%2Fclera-research-engineer-synthetic-data-12"},{"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%2Fclera-research-engineer-synthetic-data-12"},{"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/clera-research-engineer-synthetic-data-12\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fclera-research-engineer-synthetic-data-12"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3762541}},{"tool":"search_jobs","arguments":{"company":"getclera.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3762541},"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"}}