{"id":1227365,"url":"https://alion.io/job/ti-steps-aiml-engineer","title":"AI/ML Engineer","company":{"id":3800669,"name":"TI Steps","domain":"tisteps.co","url":"https://alion.io/company/ti-steps","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":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Chennai, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":21000,"max_usd":46000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":29},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon S3","optional":false},{"name":"Anthropic","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"Claude","optional":false},{"name":"Embeddings","optional":false},{"name":"EU AI Act","optional":false},{"name":"FastAPI","optional":false},{"name":"Fine-tuning","optional":false},{"name":"GCP","optional":false},{"name":"GDPR","optional":false},{"name":"Gemini","optional":false},{"name":"LLM","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"NER","optional":false},{"name":"NLP","optional":false},{"name":"OCR","optional":false},{"name":"OpenAI","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Python","optional":false},{"name":"Qdrant","optional":false},{"name":"RAG","optional":false},{"name":"Sentence-Transformers","optional":false},{"name":"spaCy","optional":false},{"name":"Gemma","optional":true},{"name":"Machine Learning","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Prompt Engineering","optional":true},{"name":"Qwen","optional":true},{"name":"Transformers","optional":true}],"status":"live","first_seen_at":"2026-09-24T11:46:11Z","employer_posted_date":null,"last_verified_at":"2026-09-24T11:46:11Z","board_verified":false,"closed_at":null,"days_open":23,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":23},"description":"We are seeking a hands-on AI/ML Engineer to build and scale a production talent-intelligence platform that parses millions of resumes into structured, auditable data and matches them to job descriptions with explainable, evidence-backed ranking. The ideal candidate combines deep NLP/document-intelligence expertise with disciplined LLM engineering - someone who treats token economics, determinism, and evaluation gates as first-class engineering concerns, not afterthoughts.\n\nLocation : Chennai \n\nType : Fulltime\n\nKey Responsibilities :\n\nHybrid Document Intelligence :\n\n- Design deterministic-first extraction pipelines (regex, gazetteers, derivation rules) with LLM tiers reserved for residual fields - targeting 75%+ token-cost reduction versus pure-LLM parsing.\n\n- Solve real-world document chaos: multi-column PDF reading order, portal-export layout variants, stacked tables, OCR routing, hidden-text and keyword-stuffing detection.\n\nLLM Engineering & Cost Optimization :\n\n- Build constrained-generation integrations (response schemas, output caps, runaway/truncation handling, graceful degradation) against Gemini/OpenAI/Claude-class APIs.\n\n- Operate batch inference at scale with per-call token accounting, cost projection, and provider abstraction.\n\n- Design escalation ladders: deterministic - residual prompt - per-field micro-prompts, with confidence-gated routing.\n\nRetrieval & Matching :\n\n- Build hybrid retrieval (BM25 + dense embeddings, reciprocal-rank fusion) over vector stores (Qdrant), with cross-encoder / LLM re-ranking and grounded, quote-verified narratives.\n\n- Implement deterministic scoring with per-tenant weights, must-have gates, and full score breakdowns for recruiter trust.\n\nEvaluation & Quality Engineering :\n\n- Own golden-set regression gates, full-corpus diff validation, LLM-as-judge audit loops, and error-taxonomy logging that feeds future fine-tuning.\n\n- Enforce precision targets on PII fields (>=98%) and date-derived arithmetic (>=97%) - values the LLM never computes.\n\nPlatform & Data Engineering :\n\n- Ship FastAPI services with typed schemas (pydantic v2), multi-tenant isolation, API-key grants, and restricted-data serving invariants.\n\n- Design MongoDB/S3-backed persistence for millions of documents with content-addressed dedup and GDPR deletion paths (atomic PII sub-documents).\n\nResponsible AI :\n\n- Maintain evidence-based skill scoring that is auditable by construction (NYC LL144 / EU AI Act context); no black-box rankings.\n\nRequired Skills & Qualifications :\n\n- Technical Expertise : Python 3.11+, pydantic, FastAPI, spaCy, embeddings (sentence-transformers/MiniLM class), MongoDB, vector databases (Qdrant/pgvector/Pinecone).\n\n- AI/ML Specialization : LLM prompt & schema engineering, constrained decoding, RAG/hybrid retrieval, NER, entity normalization & alias/discovery loops.\n\n- Engineering Discipline : deterministic/reproducible pipelines, evaluation harnesses, regression gates, token/cost accounting, CI.\n\n- Cloud Experience : S3-scale batch processing; AWS or GCP; Gemini/Bedrock/Anthropic API integration.\n\n- Soft Skills : evidence-driven decision making, writing crisp technical docs, working directly with recruiter/product feedback.\n\n- Experience : 5 - 8 years in ML/NLP or data-intensive backend engineering, with at least 2 years shipping LLM-integrated production systems.\n\nPreferred Qualifications :\n\n- Experience with resume/JD parsing, HR-tech, or search/ranking systems.\n\n- SLM fine-tuning experience (Qwen/Gemma class) and building training sets from production error logs.\n\n- Familiarity with AI hiring-regulation compliance (NYC LL144, EU AI Act) and PII/GDPR engineering.\n\n- Cross-encoder re-ranking and LLM-as-judge evaluation experience.\nSkills\nArtificial Intelligence, Machine Learning, NLP, LLM, Python, Prompt Engineering, AWS","description_format":"text","description_chars":3812,"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":[],"lifecycle":[{"event":"open","at":"2026-09-25T13:06:44Z"}],"visa":[],"liveness":{"score":44,"band":"fade","label":"Fading","p_open":0.85,"p_active":0.695,"p_room":0.75,"age_days":22,"expected_fill_days":26,"reasons":["seen:22","win:late"],"computed_at":"2026-10-17T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/ti-steps-aiml-engineer","json_url":"https://alion.io/job/ti-steps-aiml-engineer.json","meta":{"generated_at":"2026-10-17T15:25:43Z","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":20871,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-18T00:00:00Z"}},"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":3800669},"rest":"https://alion.io/mcp/rest/get_company?id=3800669"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fti-steps-aiml-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%2Fti-steps-aiml-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%2Fti-steps-aiml-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/ti-steps-aiml-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fti-steps-aiml-engineer"}]}