{"id":3002758,"url":"https://alion.io/job/e2e-networks-ai-engineer","title":"AI Engineer","company":{"id":63299,"name":"E2E Networks","domain":"e2enetworks.com","url":"https://alion.io/company/e2e-networks","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Schema","truth_index":{"grade":"B","score":75,"open_postings":4,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-26T05:57:25Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"junior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India","Delhi, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":12000,"max_usd":31000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":18},"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"DeepSpeed","optional":false},{"name":"FSDP","optional":false},{"name":"HPC","optional":false},{"name":"InfiniBand","optional":false},{"name":"Kubeflow","optional":false},{"name":"Kubernetes","optional":false},{"name":"Linux","optional":false},{"name":"Machine Learning","optional":false},{"name":"Megatron-LM","optional":false},{"name":"NCCL","optional":false},{"name":"Platform Engineering","optional":false},{"name":"PyTorch","optional":false},{"name":"Ray","optional":false},{"name":"SLURM","optional":false}],"status":"live","first_seen_at":"2026-10-21T12:35:00Z","employer_posted_date":null,"last_verified_at":"2026-10-21T12:35:00Z","board_verified":false,"closed_at":null,"days_open":5,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":5},"description":"Responsibilities: \nOwn technical success for training-cluster customers from discovery to production.\nUnderstand the customer's training workload: framework, model size, data pipeline, cluster size, GPU type, networking needs, storage needs, checkpointing strategy, and reliability expectations.\nRecommend cluster architecture across Kubernetes, Slurm, Ray, containers, storage, networking, and observability.\nHelp customers run pilots, validate cluster performance, debug jobs, and move toward production usage.\nDebug issues across NCCL, networking, storage, scheduler behavior, containers, drivers, distributed training frameworks, checkpointing, and job failures.\nCreate reusable playbooks, reference architectures, examples, and troubleshooting guides.\nBring high-signal product feedback to platform engineers: what customers are trying to train, what breaks, what is confusing, and what Jarvis Labs should improve.\nSupport pre-sales technical evaluation and post-sales workload success, without owning revenue quota.\n\nRequirements: \nStrong technical background in ML engineering, platform engineering, solutions architecture, or production training workloads.\nPractical understanding of distributed training or large-scale compute workloads. Comfortable with Kubernetes, Linux, containers, networking, storage, logs, metrics, and debugging.\nAbility to communicate clearly with ML engineers, platform teams, and customer stakeholders.\nHigh agency: you solve customer problems, synthesize patterns, and improve the system.\nStrong written communication for customer notes, internal feedback, runbooks, and examples.\n\nStrong Pluses: \nExperience with Slurm, Ray, Kubernetes, Argo, Kubeflow, Volcano, Kueue, or similar systems.\nExperience with PyTorch DDP/FSDP, DeepSpeed, Megatron-LM, NCCL, checkpointing, data loading, or multi-node training.\nExperience with InfiniBand/RDMA, GPU topology, storage bottlenecks, or HPC operations.\nExperience as an ML engineer who has actually trained or fine-tuned models on cloud GPU infrastructure.\nAbility to write scripts/tools to automate setup, validation, benchmarking, and debugging.\nSkills\nK8s, Kubernetes, ML, distributed, distributed training, machine learning","description_format":"text","description_chars":2205,"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":["Cloud Platforms (IaaS & PaaS)","AI Compute & Inference"],"lifecycle":[{"event":"open","at":"2026-10-21T12:35:00Z"}],"visa":[],"liveness":{"score":85,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.854,"p_room":1,"age_days":4,"expected_fill_days":20,"reasons":["seen:4","win:early","comp:junior"],"computed_at":"2026-10-26T05:57:25Z"},"pay":null,"html_url":"https://alion.io/job/e2e-networks-ai-engineer","json_url":"https://alion.io/job/e2e-networks-ai-engineer.json","meta":{"generated_at":"2026-10-26T18:22:26Z","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":24587,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-27T00:00:00Z"}},"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":63299},"rest":"https://alion.io/mcp/rest/get_company?id=63299"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fe2e-networks-ai-engineer"},{"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%2Fe2e-networks-ai-engineer"},{"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%2Fe2e-networks-ai-engineer"},{"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/e2e-networks-ai-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fe2e-networks-ai-engineer"}]}