{"id":2338920,"url":"https://alion.io/job/shopee-agent-reliability-evaluation-algorithm-engineer","title":"Agent Reliability & Evaluation Algorithm Engineer","company":{"id":49909,"name":"Shopee","domain":"shopee.com","url":"https://alion.io/company/shopee","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Career site","truth_index":{"grade":"A","score":100,"open_postings":12,"ghost_share":0,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":6,"computed_at":"2026-10-12T06:55:09Z"}},"role":"Industrial Engineering","role_family":"Industrial Engineering","seniority":"junior","employment_type":null,"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":null,"salary_estimate":{"min_usd":30000,"max_usd":50000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":419},"experience_years_min":1,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Context Engineering","optional":false},{"name":"DPO","optional":false},{"name":"Fine-tuning","optional":false},{"name":"Function Calling","optional":false},{"name":"GRPO","optional":false},{"name":"LLM","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Post-training","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"RAG","optional":false},{"name":"Reward Modeling","optional":false},{"name":"SFT","optional":false},{"name":"SQL","optional":false},{"name":"Tool Use","optional":false},{"name":"FSDP","optional":true},{"name":"LLaMA-Factory","optional":true},{"name":"vLLM","optional":true}],"status":"live","first_seen_at":"2026-10-12T10:56:00Z","employer_posted_date":"2026-10-12","last_verified_at":"2026-10-13T00:44:55Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"Design and own the evaluation system for LLM Agents, including benchmark construction, LLM-as-Judge with human annotation, and regression/comparison pipelines. Continuously monitor product metrics to guide Agent and model optimization.\nBuild Agent reliability analysis, including error attribution and uncertainty estimation across multi-step trajectories, and turn failure cases into targeted improvements.\nDrive evaluation-guided Agent optimization, including Harness design (planning, verification, self-refine), tool calling, context engineering, and memory.\nLead evaluation-driven post-training of LLMs for vertical domains (SFT, DPO, RL), including data pipelines and reward model design.\nBuild and optimize RAG/retrieval systems and the Agent tool layer (search, code interpreters, sandboxes, MCP) and evaluate their impact on end-to-end Agent quality.\nExplore frontier research in Agent reliability and evaluation and drive a full closed loop from research to deployment.\nMaster’s degree or above in Artificial Intelligence, Computer Science, Mathematics, or a related field.\nAt least 1 year of full-time industry experience building and deploying production LLM Agent systems (task planning, orchestration, tool calling), including designing evaluation sets and metrics (LLM-as-Judge, human annotation, error attribution) to drive iteration.\nHands-on experience fine-tuning LLMs via SFT and DPO (GRPO/RL a plus), and building and optimizing RAG/retrieval systems (recall, ranking, embedding fine-tuning).\nGood programming skills; proficient in Python (SQL and PyTorch are a plus). Familiar with training and inference frameworks such as verl, vLLM, FSDP, or LLaMA-Factory.\nStrong analytical skills, with a solid grasp of statistics and experiment design. Sustained curiosity about frontier AI, strong self-drive, and the ability to collaborate closely with teams to drive a full closed loop from research to deployment.","description_format":"text","description_chars":1928,"description_truncated":false,"requirements":{"experience_years_min":1,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Marketplaces"],"lifecycle":[{"event":"open","at":"2026-10-12T10:56:00Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":6,"reasons":["conf:1","win:early","comp:junior,brand"],"computed_at":"2026-10-13T01:49:38Z"},"pay":null,"html_url":"https://alion.io/job/shopee-agent-reliability-evaluation-algorithm-engineer","json_url":"https://alion.io/job/shopee-agent-reliability-evaluation-algorithm-engineer.json","meta":{"generated_at":"2026-10-13T01:49:38Z","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":2609,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-14T00:00:00Z"}},"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":49909},"rest":"https://alion.io/mcp/rest/get_company?id=49909"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fshopee-agent-reliability-evaluation-algorithm-engineer"},{"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%2Fshopee-agent-reliability-evaluation-algorithm-engineer"},{"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%2Fshopee-agent-reliability-evaluation-algorithm-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/shopee-agent-reliability-evaluation-algorithm-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fshopee-agent-reliability-evaluation-algorithm-engineer"}]}