{"id":2144206,"url":"https://alion.io/job/beacon-ai-software-engineer-artificial-intelligencellm","title":"Software Engineer, Artificial Intelligence/LLM","company":{"id":3354,"name":"Beacon AI","domain":"beaconai.com","url":"https://alion.io/company/beaconai","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"junior","employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"explicit","locations":["San Carlos, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":135000,"max":168000,"currency":"USD","period":"year","gross":null,"usd_annual":168000},"salary_estimate":null,"experience_years_min":2,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"A/B Testing","optional":false},{"name":"Amazon Aurora","optional":false},{"name":"Amazon S3","optional":false},{"name":"Anthropic","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"DynamoDB","optional":false},{"name":"Embeddings","optional":false},{"name":"Function Calling","optional":false},{"name":"Hallucination","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"LangChain","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"OpenAI","optional":false},{"name":"OpenSearch","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Time Series Forecasting","optional":false},{"name":"Tool Use","optional":false},{"name":"TypeScript","optional":false},{"name":"CI/CD","optional":true},{"name":"Multimodal AI","optional":true},{"name":"PostgreSQL","optional":true},{"name":"TensorRT","optional":true},{"name":"TensorRT-LLM","optional":true},{"name":"Triton","optional":true},{"name":"Weaviate","optional":true}],"status":"closed","first_seen_at":"2026-09-14T23:05:55Z","employer_posted_date":"2026-09-14","last_verified_at":"2026-10-10T02:42:13Z","board_verified":false,"closed_at":"2026-10-10T02:42:13Z","days_open":25,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":25},"description":"About Beacon AI\nWe’re a fast-moving team of aviators, engineers, and operators building an AI platform to make flying safer, more efficient, and more capable. Backed by top investors, we’ve secured a dozen Department of Defense contracts and partnered with major airlines to deliver mission-critical systems. We operate without silos or heavy processes. Small, focused teams own what they build, ship quickly, and learn fast, pushing the boundaries of how humans and AI work together in aviation.\nYou will ship LLM-powered product features end-to-end. That means designing retrieval and tool-calling flows, writing the services that run them, building evals and guardrails, and watching cost, latency, and quality in production. You’ll partner with the ML/infra teammates on embeddings, indexing, and model hosting, and with the product teammates on user experience and outcomes. We move fast, and we care about reliability in a safety-critical domain.\nThis role is for engineers early in their LLM/production ML career (2-4 years software engineering experience). You'll implement features within existing service patterns, with architecture and eval design guided by senior engineers.\nWhat you’ll do\nBuild user-facing LLM features\nDesign and implement retrieval-augmented generation and tool-calling flows using frameworks like LangChain or equivalent primitives, where simpler is better.\n\nDeliver robust JSON and schema-bound outputs with validation, retries, and fallbacks.\n\nAdd function calling to integrate with internal tools, search, routing, and data services.\n\nOwn the service layer\nShip APIs and workers in Python or TypeScript with clear contracts, streaming, and backoff.\n\nAdd caching, request shaping, prompt templates, and context packing to control latency and cost.\n\nIntegrate with AWS Bedrock, OpenAI, Anthropic, or self-hosted endpoints as needed.\n\nRetrieval and data prep\nCollaborate with infrastructure teammates to develop chunking, embeddings, and indexing capabilities for documents, time series, and multimedia.\n\nChoose and tune vector backends such as OpenSearch, pgvector, or Pinecone.\n\nKeep knowledge bases fresh with data syncs from S3, Aurora, DynamoDB, and external sources.\n\nEvaluation and quality\nCreate offline evals and golden sets for prompts, retrievers, and tools.\n\nStand up online metrics for task success, hallucination rate, retrieval precision/recall, p95 latency, and cost per request.\n\nRun A/B tests and prompt/version rollouts with guardrails and canaries.\n\nSafety, privacy, and compliance\nImplement content and policy checks, PII detection and redaction, access controls, and auditing.\n\nDesign human-in-the-loop paths for sensitive actions.\n\nHandle aviation data with care and follow internal security standards.\n\nOperate what you build\nAdd tracing, logs, and dashboards for model calls, token usage, errors, and saturation.\n\nDebug tricky failures across retrieval, prompts, tools, and providers.\n\nWhat will make you successful\nShipped LLM apps: You’ve put LLM features in front of users and improved them with data.\n\nStrong builder: Comfortable writing production code, tests, and docs. You keep things simple and observable.\n\nRAG and tools depth: You understand embeddings, chunking, vector search tradeoffs, and function calling.\n\nQuality mindset: You design evals, define success metrics, and iterate based on evidence.\n\nCost and latency aware: You track p95, hit SLAs, and reduce cost without hurting quality.\n\nClear communicator: You explain tradeoffs and align partners across product, infra, and security.\n\nGrowth mindset: You take direction well, ask good questions, and level up fast with feedback.\n\nNice to have\nExperience with Bedrock, OpenSearch Serverless, pgvector, Pinecone, or Weaviate.\n\nPrompt versioning, guardrails, and provider routing in production.\n\nMultimodal work with time series or video.\n\nFamiliarity with GPU inference, Triton, or TensorRT-LLM.\n\nAviation or other safety-critical domain exposure.\n\nDevOps basics for CI/CD, IaC, and secure secrets handling.\n\nExample problems you might tackle in month one\nTransform an internal knowledge base into a low-latency RAG service, complete with explicit schemas and evaluations.\n\nAdd tool-calling to automate a repetitive cockpit or ops workflow with guardrails and audit trails.\n\nReduce the cost per request through improved chunking, caching, and prompt refactoring, while maintaining task success rates.\n\nWork Location\n This is a hybrid role based in San Carlos, CA, with 3+ days per week onsite and the option to work remotely on remaining days.\nPerks & Benefits (Full-Time Employees)\nHealthcare: 100%* of employee medical premiums covered; 25% for dependents\n\nTime Off: 3 weeks PTO plus 13+ paid company holidays\n\n401(k): Offered (no current employer match, but we are committed to enhancing this benefit in the future)\n\nDue to U.S. export control regulations, we can only hire U.S. Persons (U.S. citizens, Green Card holders, lawful permanent residents, or individuals granted asylum or refugee status). We are unable to provide visa sponsorship or support visa transfers. All work must be performed in the United States.\nBeacon AI is an equal opportunity employer and does not discriminate based on race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, veteran status, or any other protected characteristic. We prohibit harassment or discrimination of any kind in the workplace and comply with all applicable federal, state, and local employment laws.","description_format":"text","description_chars":5556,"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":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Avionics & Flight Control","Commercial Aviation","Defense AI"],"lifecycle":[{"event":"open","at":"2026-10-09T04:02:56Z"},{"event":"close","at":"2026-10-10T02:42:13Z"}],"visa":[],"liveness":null,"pay":{"stated_usd_annual":168000,"is_top_pay":false},"html_url":"https://alion.io/job/beacon-ai-software-engineer-artificial-intelligencellm","json_url":"https://alion.io/job/beacon-ai-software-engineer-artificial-intelligencellm.json","meta":{"generated_at":"2026-10-11T02:44:40Z","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","counted_by":"address","units_charged":1,"used_today":4393,"day_limit":5000,"remaining_today":607,"minute_limit":60,"resets_at":"2026-10-12T00:00:00Z"}},"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":3354},"rest":"https://alion.io/mcp/rest/get_company?id=3354"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fbeacon-ai-software-engineer-artificial-intelligencellm"},{"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%2Fbeacon-ai-software-engineer-artificial-intelligencellm"},{"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%2Fbeacon-ai-software-engineer-artificial-intelligencellm"},{"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/beacon-ai-software-engineer-artificial-intelligencellm\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fbeacon-ai-software-engineer-artificial-intelligencellm"}]}