{"id":3539292,"url":"https://alion.io/job/valo-founding-data-scientist","title":"Founding Data Scientist","company":{"id":4488327,"name":"Valo","domain":"tellvalo.com","url":"https://alion.io/company/valo-4","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"Data Science","role_family":"Data Science","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":["Gurgaon, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":23000,"max_usd":49000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":75},"experience_years_min":7,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"DeepSpeed","optional":false},{"name":"DPO","optional":false},{"name":"FSDP","optional":false},{"name":"Function Calling","optional":false},{"name":"Gemma","optional":false},{"name":"Llama","optional":false},{"name":"LLM","optional":false},{"name":"LoRA","optional":false},{"name":"PEFT","optional":false},{"name":"Post-training","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Qwen","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"SFT","optional":false},{"name":"SGLang","optional":false},{"name":"Transformers","optional":false},{"name":"vLLM","optional":false},{"name":"GRPO","optional":true},{"name":"PPO","optional":true},{"name":"Reward Modeling","optional":true},{"name":"RLHF","optional":true}],"status":"live","first_seen_at":"2026-10-30T18:36:15Z","employer_posted_date":null,"last_verified_at":"2026-10-30T18:36:15Z","board_verified":false,"closed_at":null,"days_open":1,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":1},"description":"We're looking for a Founding Data Scientist to build and post-train language models that power autonomous AI agents. You'll own the complete model improvement lifecycle, from training data and reward design to SFT, reinforcement learning, evaluation, and production deployment. This is a deeply hands-on role working directly with the founders to build proprietary AI models that learn from real-world outcomes.\n\nResponsibilities: \nLLM Post-Training: Fine-tune open-weight models (Llama, Qwen, Gemma) using SFT, DPO, and RL techniques.\nReinforcement Learning: Design reward functions and optimize model policies using real-world task outcomes and user preferences.\nAgent Data Pipelines: Build high-quality training datasets from agent trajectories, tool interactions, and preference signals.\nModel Evaluation: Develop benchmarks to measure reasoning, tool use, decision-making, and task completion.\nTraining and Inference: Run distributed training and high-throughput inference using PyTorch, FSDP, DeepSpeed, vLLM, and SGLang.\nProduction Ownership: Deploy, optimize, and continuously improve fine-tuned models.\n\nRequirements: \nHands-on experience post-training open-weight LLMs using SFT, DPO, and/or RL techniques, with production deployment experience.\nStrong expertise in Python, PyTorch, transformers, attention mechanisms, and LLM architectures.\nExperience with LoRA/PEFT, distributed training (FSDP/DeepSpeed), mixed precision, and multi-GPU infrastructure.\nPractical experience with vLLM/SGLang for high-throughput inference and agent rollouts.\nExperience building LLM training datasets, agent trajectories, preference datasets, and evaluation frameworks.\nStrong understanding of model optimization, experimentation, and failure analysis.\nGood to Have: Experience with PPO, GRPO, RLHF, reward modeling, and long-horizon autonomous agents.\n\nIdeal Candidate: \nEngineers and scientists who have actually trained, fine-tuned, and shipped LLMs, not just built applications using LLM APIs.\nYou should enjoy solving complex ML problems, experimenting with model architectures and training techniques, and taking end-to-end ownership in a fast-moving founding team.\nSkills\nLLM, Large Language Model, PyTorch, Python, Transformers","description_format":"text","description_chars":2229,"description_truncated":false,"requirements":{"experience_years_min":7,"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":[],"lifecycle":[{"event":"open","at":"2026-10-30T18:36:15Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":1,"expected_fill_days":28,"reasons":["seen:1","win:early"],"computed_at":"2026-11-01T06:10:25Z"},"pay":null,"html_url":"https://alion.io/job/valo-founding-data-scientist","json_url":"https://alion.io/job/valo-founding-data-scientist.json","meta":{"generated_at":"2026-11-01T09:38:48Z","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":14947,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-02T00:00:00Z"}},"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":4488327},"rest":"https://alion.io/mcp/rest/get_company?id=4488327"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fvalo-founding-data-scientist"},{"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%2Fvalo-founding-data-scientist"},{"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%2Fvalo-founding-data-scientist"},{"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/valo-founding-data-scientist\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fvalo-founding-data-scientist"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3539292}},{"tool":"search_jobs","arguments":{"company":"tellvalo.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3539292},"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"}}