{"id":2769221,"url":"https://alion.io/job/secninjaz-technologies-llp-ai-engineer-agent-runtime-engineering","title":"AI Engineer Agent & Runtime Engineering","company":{"id":4442839,"name":"SecNinjaz Technologies LLP","domain":"secninjaz.com","url":"https://alion.io/company/secninjaz-technologies-llp","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"junior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Delhi, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":12500,"max_usd":31000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":12},"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"CI/CD","optional":true},{"name":"Docker","optional":true},{"name":"Embeddings","optional":true},{"name":"Function Calling","optional":true},{"name":"Git","optional":true},{"name":"LangChain","optional":true},{"name":"LangGraph","optional":true},{"name":"Linux","optional":true},{"name":"LLM","optional":true},{"name":"Model Context Protocol","optional":true},{"name":"OpenAI Agents SDK","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Python","optional":true},{"name":"RAG","optional":true},{"name":"Structured Outputs","optional":true},{"name":"Tool Use","optional":true},{"name":"vLLM","optional":true}],"status":"live","first_seen_at":"2026-10-10T19:00:11Z","employer_posted_date":null,"last_verified_at":"2026-10-10T19:00:11Z","board_verified":false,"closed_at":null,"days_open":8,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":8},"description":"AI Engineer — Agentic AI & Runtime Engineering\nCompany: SecNinjaz Technologies LLP\nExperience: Around 2 years of relevant hands-on experience\nEmployment: Full-time, on-site\nLocations: Netaji Subhash Place, New Delhi,\nAbout the opportunity\nAt SecNinjaz, we are building an AI-powered Vulnerability Assessment and Penetration Testing (VAPT) product that helps organisations identify, investigate and validate security weaknesses in authorised environments.\nWe are looking for an AI Engineer who enjoys building agentic systems and turning working prototypes into reliable product capabilities. You will develop the agent workflows, runtime services, tool integrations and context systems that enable our product to perform complex cybersecurity tasks.\nStrong AI engineering and software development skills are essential. Previous cybersecurity or VAPT experience is a plus. You will work alongside our cybersecurity specialists to understand the domain and translate their expertise into reusable AI capabilities.\nWhat you will work on\nAgentic workflows: Build agents that plan tasks, select tools, interpret results and complete multi-step workflows with clear stopping conditions.\nRuntime engineering: Implement persistent state, checkpoints, retries, timeouts, cancellation and recovery so workflows remain dependable during failures and interruptions.\nTool integration: Connect agents to security tools, APIs and internal services through structured interfaces, including Model Context Protocol (MCP) where appropriate.\nReusable agent skills: Work with security researchers to convert tested procedures into versioned, documented skills that different agents and models can use.\nContext and retrieval: Build retrieval-augmented generation (RAG), context management and memory mechanisms that provide relevant knowledge and preserve the history of an investigation.\nModel integration: Integrate and compare LLMs through model adapters, with a focus on private and self-hosted inference.\nExecution controls: Implement scope restrictions, approval steps, permissions, resource limits and isolated tool execution in the application.\nObservability: Capture tool calls, evidence references, failures, latency and resource usage to make agent behaviour understandable and debuggable.\nProduct improvement: Work with the data and evaluation engineer to diagnose failures, test changes and release improvements with regression checks and rollback support.\nWhat we are looking for\nStrong Python programming skills and experience with APIs, backend services, Git and debugging.\nHands-on experience building an LLM application or AI agent with tool calling, structured outputs and meaningful failure handling.\nFamiliarity with an agent framework such as LangGraph, an agent SDK or an equivalent custom implementation.\nUnderstanding of RAG, embeddings, context windows and the limitations of LLM-generated responses.\nWorking knowledge of asynchronous execution, databases and state management.\nComfort working with Linux, Docker and application deployment.\nAbility to write maintainable code, test your work and explain your engineering decisions.\nCuriosity about cybersecurity and willingness to learn from domain specialists.\nWe value projects you can explain, modify and debug. Relevant professional work, research and substantial personal projects can demonstrate your capabilities.\nGood to have\nFamiliarity with VAPT, web/API security, authentication, authorisation or security testing tools.\nExperience with MCP, reusable agent skills or multi-agent coordination.\nExposure to local model serving, vLLM, model gateways or GPU inference optimisation.\nExperience with PostgreSQL, vector databases, queues, tracing or CI/CD.\nExperience deploying AI applications in private or on-premises environments.\nYou do not need experience with every technology listed.\nWhat you will gain\nHands-on experience with SecNinjaz's on-premises NVIDIA H200 GPU infrastructure for product development, inference and experimentation.\nAn opportunity to deepen your expertise in agentic AI, model serving and dependable AI systems.\nDirect collaboration with cybersecurity researchers and engineers on practical security problems.\nOwnership of product capabilities from implementation through evaluation and deployment.\nYour initial contribution\nBuild an end-to-end agent workflow with useful execution traces, integrated tools and reliable recovery. Work with the security team to assess its results and with the evaluation engineer to measure improvements across releases.\nHow to apply \nApply through LinkedIn with your CV and one or two relevant project links, or a short technical write-up describing what you built and your contribution.\n\nor Send email your CV to [HIDDEN TEXT] with details of your completed and ongoing AI/agentic AI projects, your specific contributions, current CTC, expected CTC, and notice period or earliest date you can join SecNinjaz.","description_format":"text","description_chars":4931,"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":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Information Security"],"lifecycle":[{"event":"open","at":"2026-10-17T03:17:59Z"}],"visa":[],"liveness":{"score":70,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.782,"p_room":0.9,"age_days":8,"expected_fill_days":19,"reasons":["seen:8","win:mid","comp:junior"],"computed_at":"2026-10-19T05:45:15Z"},"pay":null,"html_url":"https://alion.io/job/secninjaz-technologies-llp-ai-engineer-agent-runtime-engineering","json_url":"https://alion.io/job/secninjaz-technologies-llp-ai-engineer-agent-runtime-engineering.json","meta":{"generated_at":"2026-10-19T18:34:56Z","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":14443,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-20T00:00:00Z"}},"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":4442839},"rest":"https://alion.io/mcp/rest/get_company?id=4442839"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fsecninjaz-technologies-llp-ai-engineer-agent-runtime-engineering"},{"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%2Fsecninjaz-technologies-llp-ai-engineer-agent-runtime-engineering"},{"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%2Fsecninjaz-technologies-llp-ai-engineer-agent-runtime-engineering"},{"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/secninjaz-technologies-llp-ai-engineer-agent-runtime-engineering\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fsecninjaz-technologies-llp-ai-engineer-agent-runtime-engineering"}]}