{"id":855001,"url":"https://alion.io/job/imagine-agent-infrastructure-engineer-core-harness-superagent","title":"Agent Infrastructure Engineer — Core Harness (Superagent)","company":{"id":691853,"name":"ImagineArt","domain":"imagine.art","url":"https://alion.io/company/imagine-5","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"A","score":92,"open_postings":8,"ghost_share":0,"stale_share":0.125,"repost_share":0,"time_to_fill_p50_days":75,"computed_at":"2026-10-03T05:45:00Z"}},"role":"DevOps","role_family":"DevOps","seniority":"middle","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":[],"countries":[],"hiring_countries":["IN"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":11500,"max_usd":32000,"period":"year","method":"role_seniority_country_cell","sample_n":19},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"A/B Testing","optional":false},{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"AutoGen","optional":false},{"name":"CrewAI","optional":false},{"name":"Function Calling","optional":false},{"name":"LangGraph","optional":false},{"name":"LLM","optional":false},{"name":"OpenAI Agents SDK","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"Structured Outputs","optional":false},{"name":"Tool Use","optional":false},{"name":"TypeScript","optional":false},{"name":"Docker","optional":true},{"name":"DSPy","optional":true},{"name":"Kubernetes","optional":true},{"name":"LangChain","optional":true},{"name":"LlamaIndex","optional":true},{"name":"Model Context Protocol","optional":true},{"name":"RAG","optional":true}],"status":"live","first_seen_at":"2026-08-18T17:41:51Z","employer_posted_date":"2026-08-18","last_verified_at":"2026-10-04T01:04:31Z","board_verified":true,"closed_at":null,"days_open":46,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":46},"description":"About ImagineArt\nWe're redefining how the world creates and designs.\nImagineArt is one of the fastest-growing GenAI companies in the world. We've scaled faster than most funded startups - with zero outside funding.\n$35M+ ARR crossed this year\n\n100M+ social impressions\n\nBuilt and shipped our own image generation model, now ranked #3 globally for photo realism\n\nNo funding. No shortcuts. Just a sharp, driven team building one of the strongest GenAI products in the world - and we're just getting started.\nWe're looking for an Agent Infrastructure Engineer to own Superagent, our core agent harness that powers conversations, tool calls, and multi-step agentic workflows across our AI products.\nThis is a deep systems and infrastructure role - not prompt engineering and not simply wrapping model APIs. You'll work on the core orchestration loop, tool-calling infrastructure, context and memory management, streaming, retries, evaluation, observability, and performance.\nKey Responsibilities\nOwn the architecture, development, and evolution of Superagent, our core agent harness.\n\nDesign and optimize the agent execution loop for latency, reliability, token efficiency, cost, and task completion.\n\nBuild and improve core harness systems including context management, memory/state handling, tool routing, function schemas, structured outputs, retries, and error recovery.\n\nBuild and maintain agent evaluation infrastructure to measure quality and guide engineering decisions with data.\n\nIntegrate and benchmark multiple LLM providers and models, evaluating performance, cost, reliability, and capabilities.\n\nImplement performance optimizations such as caching, batching, parallel tool execution, and prompt/context compression.\n\nBuild deep observability and instrumentation across agent runs, including tracing, logging, metrics, and regression detection.\n\nExtend and customize underlying agent frameworks when existing abstractions are insufficient.\n\nBuild reliable integrations with evolving AI and tool ecosystems.\n\nWork closely with product engineering teams to expose clean abstractions while keeping harness complexity behind the platform.\n\nDebug and resolve complex issues across non-deterministic, distributed, and model-driven systems.\n\nRequired Skills & Qualifications\n4+ years of experience in software engineering, backend engineering, or systems infrastructure.\n\nStrong proficiency in Python and/or TypeScript.\n\nHands-on experience building or operating LLM-based agents in production.\n\nStrong understanding of tool calling, function schemas, context limits, structured outputs, model failures, and unreliable LLM behavior.\n\nExperience with at least one agent framework such as LangGraph, OpenAI Agents SDK, CrewAI, AutoGen, or a custom/homegrown agent harness.\n\nStrong understanding of agent orchestration and multi-step workflows.\n\nExperience building or working with evaluation suites, benchmarks, A/B testing, or other measurement systems for AI products.\n\nStrong understanding of concurrency, caching, profiling, performance optimization, and latency/cost tradeoffs.\n\nExperience working with LLM APIs and production AI infrastructure.\n\nExcellent debugging and problem-solving skills, especially for complex and non-deterministic systems.\n\nPassionate about technology, self-driven, and proactive with a strong builder mindset.\n\nOptional / Nice-to-Have Skills\nContributions to open-source agent frameworks, LLM tooling, or AI infrastructure.\n\nExperience with RAG pipelines, vector databases, or long-term memory systems for AI agents.\n\nFamiliarity with MCP (Model Context Protocol) or similar tool-integration standards.\n\nExperience with LLM inference infrastructure, model routing, rate limits, fallbacks, or high-volume model APIs.\n\nExperience with LangChain, LlamaIndex, LangGraph, DSPy, or similar AI infrastructure frameworks.\n\nExperience with Kubernetes, Docker, cloud infrastructure, or distributed systems.\n\nExperience building internal developer platforms or infrastructure used by multiple engineering/product teams.\n\nStrong background in observability, distributed tracing, and production reliability.\n\nContributions to open-source projects or personal AI infrastructure projects.\n\nWhy Join Us?\nOwn the core agent infrastructure behind our AI products - every improvement you make can multiply across the entire platform.\n\nWork on real production-scale AI systems, not demo agents or simple API wrappers.\n\nSolve challenging problems across LLMs, distributed systems, orchestration, performance, and infrastructure.\n\nHave direct influence over the architecture and technical roadmap of our entire agent stack.\n\nCollaborate with a passionate and talented team building some of the most ambitious GenAI products in the market.\n\nCompetitive salary and benefits package.\n\nA culture that encourages ownership, experimentation, learning, and data-driven engineering.","description_format":"text","description_chars":4885,"description_truncated":false,"requirements":{"experience_years_min":4,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"India","iso":"IN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Media & Entertainment","Film Production"],"lifecycle":[{"event":"open","at":"2026-09-13T05:56:36Z"}],"visa":[],"liveness":{"score":71,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.788,"p_room":0.9,"age_days":45,"expected_fill_days":75,"reasons":["conf:8","velocity","win:mid"],"computed_at":"2026-10-03T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/imagine-agent-infrastructure-engineer-core-harness-superagent","json_url":"https://alion.io/job/imagine-agent-infrastructure-engineer-core-harness-superagent.json","meta":{"generated_at":"2026-10-04T01:39:23Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":2136,"day_limit":5000,"remaining_today":2864,"minute_limit":60,"resets_at":"2026-10-05T00:00:00Z"}}}