{"id":1029050,"url":"https://alion.io/job/safe-security-sde-iii-engineering-productivity-ai","title":"SDE III - Engineering Productivity (AI)","company":{"id":48325,"name":"Safe Security","domain":"safe.security","url":"https://alion.io/company/safe-security","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Lever","truth_index":{"grade":"A","score":86,"open_postings":11,"ghost_share":0,"stale_share":0.364,"repost_share":0,"time_to_fill_p50_days":111,"computed_at":"2026-10-15T05:46:00Z"}},"role":"Backend","role_family":"Backend","seniority":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":6,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"CI/CD","optional":false},{"name":"Git","optional":false},{"name":"Go","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"Incident Management","optional":false},{"name":"Java","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Python","optional":false},{"name":"Context Engineering","optional":true},{"name":"Function Calling","optional":true},{"name":"GitHub","optional":true},{"name":"GitLab","optional":true},{"name":"Kubernetes","optional":true},{"name":"Model Context Protocol","optional":true},{"name":"RAG","optional":true},{"name":"Tool Use","optional":true}],"status":"live","first_seen_at":"2026-09-18T11:34:47Z","employer_posted_date":"2026-09-18","last_verified_at":"2026-10-15T08:19:14Z","board_verified":true,"closed_at":null,"days_open":26,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":26},"description":"This role exists to change how engineering at Safe gets work done - not to add AI tools on top of today's workflow, but to rebuild the engineering operating model around AI, automation, and redesigned process, and to prove the gain in numbers.\nYou will look across the full lifecycle - requirements, design, implementation, review, testing, deployment, operations, incidents, documentation - find where engineers lose time, and decide what actually fixes it: an AI agent, an automation, a platform capability, or a process change. Then build it to production quality, drive adoption, and measure whether cycle time moved.\nThis is not a Developer Experience, DevOps, or internal-tools role. It is a software engineering role whose product is engineering throughput.\nWhy This Role Exists\nEngineering output is the constraint on how fast we ship against Fortune 500 demand. AI can lift it - but most organizations bolt AI onto unchanged workflows and get a chat window. The leverage is in redesigning the workflow around what AI can now do, putting agents inside CI, review, testing, and incident response, giving them real engineering context, and setting guardrails so engineers move fast without lowering the bar.\nThe objective is not AI adoption. It is materially higher engineering output, speed, and quality.\nWhat You'll Do:\nind the bottlenecks: Instrument how engineering time is actually spent - cycle time, review latency, CI failures, test authoring, operational toil, onboarding - and rank problems by recoverable hours.\n\nPick the right instrument: Decide per bottleneck whether the answer is AI, automation, conventional software, or process change. Reject AI where it's the wrong tool.\n\nApply AI across the lifecycle: AI-assisted development and refactoring, first-pass code review, test generation and suite optimization, automated documentation and release notes, design analysis, automated migrations, AI-assisted debugging, incident investigation, and root-cause analysis.\n\nBuild engineering agents: Agents that diagnose CI failures, investigate production issues, write tests, run dependency upgrades, propose security fixes, analyze PRs, and execute repetitive migrations - human-in-the-loop by default, autonomy earned per workflow.\n\nRedesign the process: Rework code review, testing, CI, and incident management for a world where AI does the first pass - and define what stays human-owned and where approval is mandatory.\n\nBuild the platform: AI gateway, agent runtime and workflow orchestration, codebase intelligence, engineering context retrieval, and deep Git/CI/observability/ticketing integrations - plus APIs and SDKs so teams build their own AI workflows on it.\n\nSolve the context problem: Give agents permission-aware access to code, architecture docs, service ownership, deployment state, telemetry, incidents, and standards - and own retrieval quality and freshness.\n\nSet the guardrails: Quality, security, privacy, access control, approval gates, auditability, and evaluation for AI-generated change.\n\nProve the impact and drive adoption: Baseline, experiment, publish results, kill what doesn't move the metric, and mentor teams into the patterns that work.\n\nHow We Measure Success:\nNot by tools built, experiments run, LLM calls, or chatbot users. By outcomes: reduced cycle time and repetitive work, faster PR review and CI failure resolution, fewer escaped defects, faster incident diagnosis, less operational toil, shorter onboarding, higher deployment frequency and throughput, and real adoption of AI workflows.\nWhat We're Looking For:\n6+ years building production software, with SDE3-level ownership of systems in production.\n\nStrong Python, Java, Go, or equivalent - you ship production services and review others' code.\n\nSolid distributed systems, API and microservice, and software architecture grounding.\n\nHands-on cloud infrastructure and CI/CD experience.\n\nDemonstrated developer tooling and automation work that other engineers actually used.\n\nPractical experience with LLMs and agentic systems in real systems, not only experiments.\n\nAbility to reason quantitatively about workflows: baseline, hypothesis, experiment, measured result.\n\nStrong writing and the ability to influence engineering teams without authority.\n\nNice to Have\nLLM APIs and model orchestration · production AI agents with tool use · RAG, retrieval, and vector databases · MCP or similar tool/context protocols · LLM evaluation, prompt and context engineering, AI observability · GitHub/GitLab APIs and deep CI/CD integration · Kubernetes and cloud platforms · internal developer platforms · DORA/SPACE-style engineering measurement · security or compliance-bound environments.\nSDE3 Expectations\nNot an execution-only role. You identify org-wide productivity problems without being handed a backlog, work across teams, read both technical and process bottlenecks, build for scale rather than prototypes, influence without authority, prove improvements quantitatively, and mentor engineers into AI-first ways of working.\nWhat Success Looks Like:\nIn 90 days: Engineering time-spend is baselined, top bottlenecks are quantified in recoverable hours, and the first automation is shipped and in use.\n\nAI does the first pass: Code review, test generation, and CI failure diagnosis run through AI workflows by default; humans review judgment, not mechanics.\n\nCycle time drops measurably quarter over quarter, attributable to specific changes.\n\nAgents carry real load across defined workflows, with approval gates, audit trails, and tracked reliability - while escaped defects and security findings do not rise.","description_format":"text","description_chars":5618,"description_truncated":false,"requirements":{"experience_years_min":6,"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":["Artificial Intelligence","Threat Intelligence","Information Security","Cybersecurity AI"],"lifecycle":[{"event":"open","at":"2026-09-18T13:02:06Z"}],"visa":[],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.897,"p_room":1,"age_days":26,"expected_fill_days":111,"reasons":["conf:1","velocity","win:early"],"computed_at":"2026-10-15T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/safe-security-sde-iii-engineering-productivity-ai","json_url":"https://alion.io/job/safe-security-sde-iii-engineering-productivity-ai.json","meta":{"generated_at":"2026-10-15T10:04:11Z","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":15174,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-16T00:00:00Z"}},"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":48325},"rest":"https://alion.io/mcp/rest/get_company?id=48325"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fsafe-security-sde-iii-engineering-productivity-ai"},{"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%2Fsafe-security-sde-iii-engineering-productivity-ai"},{"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%2Fsafe-security-sde-iii-engineering-productivity-ai"},{"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/safe-security-sde-iii-engineering-productivity-ai\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fsafe-security-sde-iii-engineering-productivity-ai"}]}