{"id":726960,"url":"https://alion.io/job/vichara-ai-software-engineer","title":"AI Software Engineer","company":{"id":697687,"name":"Vichara","domain":"vichara.com","url":"https://alion.io/company/vichara","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"SmartRecruiters","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bogotá, Colombia"],"countries":["CO"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":23000,"max_usd":60000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":2365},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Amazon EKS","optional":false},{"name":"AWS","optional":false},{"name":"Azure AKS","optional":false},{"name":"Azure DevOps","optional":false},{"name":"BERT","optional":false},{"name":"CI/CD","optional":false},{"name":"Docker","optional":false},{"name":"ElasticSearch","optional":false},{"name":"Embeddings","optional":false},{"name":"FAISS","optional":false},{"name":"FastAPI","optional":false},{"name":"Fine-tuning","optional":false},{"name":"Git","optional":false},{"name":"GPT-4","optional":false},{"name":"Hallucination","optional":false},{"name":"Kubernetes","optional":false},{"name":"LanceDB","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LLM","optional":false},{"name":"Mistral","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"NumPy","optional":false},{"name":"OpenTelemetry","optional":false},{"name":"Pandas","optional":false},{"name":"Pinecone","optional":false},{"name":"Prometheus","optional":false},{"name":"Promptfoo","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Redis","optional":false},{"name":"Rest API","optional":false},{"name":"Sentence-Transformers","optional":false},{"name":"Sentiment Analysis","optional":false},{"name":"SigNoz","optional":false},{"name":"SQL","optional":false},{"name":"Azure","optional":true},{"name":"Transformers","optional":true}],"status":"live","first_seen_at":"2025-12-31T14:49:55Z","employer_posted_date":"2025-12-31","last_verified_at":"2026-10-31T08:30:17Z","board_verified":true,"closed_at":null,"days_open":303,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":303},"description":"Vichara is a Financial Services focused products and services firm headquartered in NY and building systems for some of the largest i-banks and hedge funds in the world.\n Key Responsibilities\nArchitecture & System Design\nArchitect, design, and lead multi-agent LLM systems using LangGraph, LangChain, and Promptfoo for prompt lifecycle management and benchmarking.\n\nBuild Retrieval-Augmented Generation (RAG) pipelines leveraging hybrid vector search (dense + keyword) using LanceDB, Pinecone, or Elasticsearch.\n\nDefine system workflows for summarization, query routing, retrieval, and response generation, ensuring minimal latency and high precision.\n\nDevelop RAG evaluation frameworks combining retrieval precision/recall, hallucination detection, and latency metrics - aligned with analyst and business use cases.\n\nAI Model Integration & Fine-Tuning\nIntegrate GPT-4o, PaLM 2, and open-weight models (LLaMA, Mistral) for task-specific contextual Q&A.\n\nFine-tune transformer models (BERT, SentenceTransformers) for document classification, summarization, and sentiment analysis.\n\nManage prompt routing and variant testing using Promptfoo or equivalent tools.\n\nAgentic AI & Orchestration\nImplement multi-agent architectures with modular flows - enabling task-specific agents for summarization, retrieval, classification, and reasoning.\n\nDesign fallback and recovery behaviors to ensure robustness in production.\n\nEmploy LangGraph for parallel and stateful agent orchestration, error recovery, and deterministic flow control.\n\nData Engineering & RAG Infrastructure\nArchitect ingestion pipelines for structured and unstructured data - including financial statements, filings, and PDF documents.\n\nLeverage MongoDB for metadata storage and Redis Streams for async task execution and caching.\n\nImplement vector-based search and retrieval layers for high-throughput and low-latency AI systems.\n\nObservability & Production Deployment\nDeploy end-to-end AI systems on AWS EKS / Azure Kubernetes Service, integrated with CI/CD pipelines (Azure DevOps).\n\nBuild comprehensive monitoring dashboards using OpenTelemetry and Signoz, tracking latency, retrieval precision, and application health.\n\nEnforce testing and regression validation using golden datasets and structured assertion checks for all LLM responses.\n\nCross-functional Collaboration\nCollaborate with DevOps, MLOps, and application development teams to integrate AI APIs with React / FastAPI -based user interfaces.\n\nWork with business analysts to translate credit, compliance, and customer-support requirements into actionable AI agent workflows.\n\nMentor a small team of GenAI developers and data engineers in RAG, embeddings, and orchestration techniques.\n\n Experience:5+ years as an AI or ML Engineer\n\nRequired Skills & Experience\n\nLLMs & GenAI: GPT-4o, PaLM 2, LangGraph, LangChain, Promptfoo, SentenceTransformers\n\nRAG Frameworks: LanceDB, Pinecone, ElasticSearch, FAISS, MongoDB\n\nAgentic AI: LangGraph multi-agent orchestration, routing logic, task decomposition\n\nFine-Tuning: BERT / domain-specific transformer tuning, evaluation framework design\n\nInfra & MLOps: FastAPI, Docker, Kubernetes (EKS/AKS), Redis Streams, Azure DevOps CI/CD\n\nMonitoring: OpenTelemetry, Signoz, Prometheus\n\nLanguages & Tools: Python, SQL, REST APIs, Git, Pandas, NumPy\n\nNice-to-Have Skills\n\nKnowledge of Reranker-based retrieval (MiniLM / CrossEncoder)\n\nFamiliarity with Prompt evaluation and scoring (BLEU, ROUGE, Faithfulness)\n\nDomain exposure to Credit Risk, Banking, and Investment Analytics\n\nExperience with RAG benchmark automation and model evaluation dashboards","description_format":"text","description_chars":3602,"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":[{"language":"English","level":"All levels","optional":false}]},"benefits":[],"hiring_locations":[{"name":"Colombia","iso":"CO","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Financial Software & Embedded Finance","Online Brokerage & Trading Platforms"],"lifecycle":[{"event":"open","at":"2026-09-11T08:41:41Z"}],"visa":[],"liveness":{"score":8,"band":"cold","label":"Long shot","p_open":1,"p_active":0.27,"p_room":0.28,"age_days":303,"expected_fill_days":36,"reasons":["conf:1","win:tail","crowd:"],"computed_at":"2026-10-31T05:58:55Z"},"pay":null,"html_url":"https://alion.io/job/vichara-ai-software-engineer","json_url":"https://alion.io/job/vichara-ai-software-engineer.json","meta":{"generated_at":"2026-10-31T09:18:50Z","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":14078,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-01T00:00:00Z"}},"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":697687},"rest":"https://alion.io/mcp/rest/get_company?id=697687"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fvichara-ai-software-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%2Fvichara-ai-software-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%2Fvichara-ai-software-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/vichara-ai-software-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fvichara-ai-software-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":726960}},{"tool":"search_jobs","arguments":{"company":"vichara.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":726960},"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"}}