{"id":2503689,"url":"https://alion.io/job/firebird-ml-engineer-inference-and-serving","title":"ML Engineer, Inference and Serving","company":{"id":2031237,"name":"Firebird","domain":"firebird.ai","url":"https://alion.io/company/firebird-ai","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Spark","truth_index":{"grade":"C","score":58,"open_postings":13,"ghost_share":0.692,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-15T05:46:00Z"}},"role":"AI/ML","role_family":"AI/ML","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":["Yerevan, Armenia"],"countries":["AM"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWQ","optional":false},{"name":"GPTQ","optional":false},{"name":"Grafana","optional":false},{"name":"Hugging Face","optional":false},{"name":"KV Cache","optional":false},{"name":"LLM","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"Machine Learning","optional":false},{"name":"Mixture of Experts","optional":false},{"name":"OpenAI","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Quantization","optional":false},{"name":"SGLang","optional":false},{"name":"Speculative Decoding","optional":false},{"name":"TensorRT","optional":false},{"name":"TensorRT-LLM","optional":false},{"name":"Triton","optional":false},{"name":"Triton Inference Server","optional":false},{"name":"vLLM","optional":false},{"name":"Embeddings","optional":true},{"name":"Gateway API","optional":true},{"name":"Helm","optional":true},{"name":"InfiniBand","optional":true},{"name":"Kubernetes","optional":true},{"name":"LoRA","optional":true},{"name":"NCCL","optional":true},{"name":"NVLink","optional":true},{"name":"ONNX","optional":true},{"name":"PEFT","optional":true}],"status":"live","first_seen_at":"2026-05-25T00:00:00Z","employer_posted_date":"2026-05-25","last_verified_at":"2026-10-15T17:42:38Z","board_verified":true,"closed_at":null,"days_open":143,"trust":{"level":"ghost","repost_count":0,"flags":["stale","company_stale"],"days_open":143},"description":"About the Role\nWe are looking for an experienced ML Engineer to help build, deploy, and optimize machine learning systems in production. In this role, you will focus on model serving, inference performance, and scalable deployment of large language models, working closely with platform and infrastructure teams to deliver reliable and efficient AI solutions.\nWhat You'll Do\nDesign, deploy, and optimize large language model (LLM) inference systems for production environments\nEvaluate, benchmark, and improve serving performance across latency, throughput, memory utilization, and cost-efficiency metrics\nImplement and optimize model-serving solutions using frameworks such as vLLM, TensorRT-LLM, SGLang, Triton Inference Server, or similar technologies\nDevelop and maintain model conversion, deployment, and evaluation workflows across the inference stack\nApply and validate quantization techniques to improve performance while preserving model quality\nProfile GPU workloads, identify bottlenecks, and drive performance improvements using industry-standard observability and profiling tools\nCollaborate with Platform, Infrastructure, and Product Engineering teams to deploy and operate scalable AI services\nContribute to architecture decisions related to distributed inference, model serving, caching strategies, and resource utilization\nImprove reliability, monitoring, and operational excellence of production inference systems\nStay current with emerging advancements in LLM serving, inference optimization, and AI infrastructure technologies, and help evaluate their adoption\nWhat We’re Looking For\n3+ years ML engineering focused on model deployment and inference, not primarily training or application-layer LLM work.\nProduction ownership of at least two of vLLM, SGLang, TensorRT-LLM under real traffic. You have diagnosed and fixed what each one does when it is misconfigured.\nLLM inference internals: attention, KV cache, prefill versus decode, memory-bandwidth-bound versus compute-bound regimes, continuous batching, chunked prefill.\nSpeculative decoding in production: EAGLE-3, ngram, suffix or draft-model approaches; calibrating draft depth and acceptance rate against concurrency.\nMoE model serving: expert parallelism, attention data-parallel, the interaction with tensor parallelism and KV capacity.\nQuantization applied and validated on production models, at least one of FP8, INT8, AWQ, GPTQ, MXFP4, including measuring the accuracy impact, not only the throughput gain.\nOpenAI chat-completions conformance at the engine level: chat templates, tool-call and reasoning parsers, streaming semantics and usage blocks, cancellation behaviour.\nBenchmarking methodology: TTFT, ITL, goodput, closed versus open loop, user-centric load; hands-on with AIPerf or GenAI-Perf.\nAccuracy and quality evaluation: has built or operated an evaluation harness (lm-eval or equivalent) to validate quantized or speculative variants against a baseline.\nGPU performance diagnosis with Nsight Systems, DCGM, nvidia-smi and engine metrics; can explain a throughput regression from a Grafana board.\nStrong Python; working PyTorch and Hugging Face model formats, tokenizers and chat templates.\nNice to Have\nGPU hardware characteristics: HBM bandwidth versus compute, NVLink topology, tensor cores; hands-on with H100, L40S, B200-class.\nKV-aware routing from the model side: llm-d, Gateway API Inference Extension (InferencePool/EPP), NVIDIA Dynamo disaggregated serving.\nPrefix caching in operation: block-hash versus prefix-tree, multi-tenant isolation.\nEmbeddings and reranking model serving, including multi-model bundles on Triton.\nTriton Inference Server\nMulti-node tensor parallelism: NCCL tuning, RDMA and InfiniBand, GPUDirect.\nKubernetes and Helm sufficient to read and edit a variant's rendered deployment.\nLoRA multi-adapter serving.\nModel export and compilation workflows (ONNX, TensorRT)","description_format":"text","description_chars":3894,"description_truncated":false,"requirements":{"experience_years_min":3,"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":["Data Centers & Colocation","AI Compute & Inference"],"lifecycle":[{"event":"open","at":"2026-10-14T06:59:58Z"}],"visa":[],"liveness":{"score":5,"band":"cold","label":"Long shot","p_open":1,"p_active":0.161,"p_room":0.28,"age_days":143,"expected_fill_days":20,"reasons":["conf:3","stale_co","ghost","win:tail","crowd:"],"computed_at":"2026-10-15T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/firebird-ml-engineer-inference-and-serving","json_url":"https://alion.io/job/firebird-ml-engineer-inference-and-serving.json","meta":{"generated_at":"2026-10-15T18:04:00Z","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":27374,"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":2031237},"rest":"https://alion.io/mcp/rest/get_company?id=2031237"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Ffirebird-ml-engineer-inference-and-serving"},{"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%2Ffirebird-ml-engineer-inference-and-serving"},{"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%2Ffirebird-ml-engineer-inference-and-serving"},{"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/firebird-ml-engineer-inference-and-serving\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ffirebird-ml-engineer-inference-and-serving"}]}