{"id":3794603,"url":"https://alion.io/job/sivad-consulting-software-engineer-agent-harness-evaluation","title":"Software Engineer, Agent Harness & Evaluation","company":{"id":3832647,"name":"SIVAD Consulting","domain":"sivadconsulting.com","url":"https://alion.io/company/sivad-consulting","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Manatal","truth_index":null},"role":"Backend","role_family":"Backend","seniority":"middle","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Jose, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":180000,"max":325000,"currency":"USD","period":"year","gross":null,"usd_annual":325000},"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"LLM","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"Python","optional":false},{"name":"TypeScript","optional":false}],"status":"live","first_seen_at":"2026-11-05T08:36:48Z","employer_posted_date":"2026-11-05","last_verified_at":"2026-11-06T09:13:21Z","board_verified":true,"closed_at":null,"days_open":1,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":1},"description":"Software Engineer, Agent Harness & Evaluation - San Jose, CA\n$180k to $325k\nWe are hiring Software Engineers to improve the performance, reliability, and efficiency of AI agents for hardware applications. You'll identify failure modes, design and run evaluations, develop new agent capabilities, and turn successful experiments into production software. You'll join a sizable, rapidly growing team of software engineers, researchers, hardware experts, customers, and founding and field teams, working across customer discovery, evaluation design, applied research, product development, and deployment for a broad range of hardware-engineering problems.\nResponsibilities\nFinding where AI agents fail, then designing and running evaluations to improve their performance, reliability, and efficiency\nBuilding new agent capabilities, including tool interfaces, context management, memory, and multi-step or multi-agent orchestration\nDigging into traces and experiment results to find bottlenecks, and telling real improvements apart from benchmark noise\nWorking with customers and domain experts to understand what they need, then shipping and maintaining fixes from start to finish (within about 3 months)\nTurning successful experiments into well-built, maintainable production software\nQualifications\nStrong software engineering skills, particularly in Python and TypeScript.\nFamiliarity with modern language models, agent systems, and common ML workflows.\nStrong communication skills, customer judgment, and the ability to identify the crux of ambiguous technical problems.\nSelf-directed and ambitious, with strong ownership, creativity, and product judgment.\nStrong commitment to customer and business outcomes.\nExperience with LLM agents, orchestration, tools, memory, tracing, ML inference, and transformer architectures\nAbility to interface directly with customers to understand requirements and deliver technical solutions\n3 - 15 years of experience as a software engineer with work on large-scale agent systems\nExperience at a rigorous tech company (Applied Intuition, Palantir, Tesla, etc.) or AI startup (Fireworks, Harvey, Y Combinator companies, etc.)\nNice to Haves\nInterest in EDA, RTL, or hardware-software systems.\nExperience or interest in electronic design automation (EDA), semiconductor domains, RTL, or hardware-software systems\nEducation\nBachelor's in CS, EE, or similar degree from a top university","description_format":"text","description_chars":2417,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Recruiting & Staffing"],"lifecycle":[{"event":"open","at":"2026-11-05T08:36:48Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":0,"expected_fill_days":26,"reasons":["conf:1","velocity","win:early"],"computed_at":"2026-11-06T05:58:05Z"},"pay":{"stated_usd_annual":325000,"is_top_pay":true},"html_url":"https://alion.io/job/sivad-consulting-software-engineer-agent-harness-evaluation","json_url":"https://alion.io/job/sivad-consulting-software-engineer-agent-harness-evaluation.json","meta":{"generated_at":"2026-11-06T12:15:00Z","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":22247,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-07T00:00:00Z"}},"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":3832647},"rest":"https://alion.io/mcp/rest/get_company?id=3832647"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fsivad-consulting-software-engineer-agent-harness-evaluation"},{"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%2Fsivad-consulting-software-engineer-agent-harness-evaluation"},{"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%2Fsivad-consulting-software-engineer-agent-harness-evaluation"},{"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/sivad-consulting-software-engineer-agent-harness-evaluation\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fsivad-consulting-software-engineer-agent-harness-evaluation"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3794603}},{"tool":"search_jobs","arguments":{"company":"sivadconsulting.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3794603},"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"}}