{"id":2241241,"url":"https://alion.io/job/htec-ai-inference-engineer","title":"AI Inference Engineer","company":{"id":55786,"name":"HTEC","domain":"htec.com","url":"https://alion.io/company/htec","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Career sitemap","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":"2026-10-12T06:55:09Z"}},"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":["Belgrade, Serbia","Serbia","Bosnia and Herzegovina","North Macedonia","Hungary","Croatia","Spain","Czech Republic"],"countries":["RS","BA","MK","HU","HR","ES","CZ"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Apache TVM","optional":false},{"name":"C++","optional":false},{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"DeepSpeed","optional":false},{"name":"IREE","optional":false},{"name":"Linux","optional":false},{"name":"LLVM","optional":false},{"name":"Machine Learning","optional":false},{"name":"MLIR","optional":false},{"name":"NLP","optional":false},{"name":"ONNX Runtime","optional":false},{"name":"OpenCL","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"PyTorch C++","optional":false},{"name":"Quantization","optional":false},{"name":"TensorFlow","optional":false},{"name":"TensorFlow C++","optional":false},{"name":"TensorRT","optional":false},{"name":"Triton Inference Server","optional":false},{"name":"vLLM","optional":false},{"name":"XLA","optional":false}],"status":"live","first_seen_at":"2026-08-20T00:00:00Z","employer_posted_date":"2026-08-20","last_verified_at":"2026-10-13T02:15:04Z","board_verified":true,"closed_at":null,"days_open":54,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":54},"description":"Be part of the team creating the software foundation for next-generation AI compute platforms. In this role, you’ll work across the full stack - from low-level kernels and hardware-optimized operators to large-scale ML deployment frameworks - in close collaboration with compiler developers, ML scientists, and hardware specialists. This position offers the chance to contribute to state-of-the-art AI infrastructure, fine-tune software for custom hardware, and deepen your expertise in system software and machine learning. \nHow You’ll Contribute:\nBuild and optimize inference pipelines for large-scale model serving (LLMs and beyond) \nWork with frameworks like PyTorch, TensorRT, and vLLM to deploy models efficiently \nImplement and optimize ML models using techniques such as quantization (INT8/FP8), kernel fusion, and efficient batching \nOptimize and implement core ML operators (e.g., GEMMs, convolutions, activations, ...) \nInvestigate and resolve issues through system-level debugging and performance analysis \nDefine and apply practices for testing, deployment, and scaling AI systems \n\nRequired skills: \nBSc/MSc in Computer Science, Engineering, Mathematics, or related discipline \nStrong programming skills in C/C++ or Python in Linux environments using common development tools \nSolid knowledge of computer architecture, system software, data structures \nHands-on experience implementing algorithms in high-level languages (C/C++/Python) \nExposure to specialized hardware (GPUs, FPGAs, DSPs, AI accelerators) and frameworks such as OpenCL or CUDA \nExperience designing or working with high-performance software systems \nSolid knowledge of ML fundamentals \nMotivated team player with a strong sense of responsibility \nYou are a great fit if you have experience in at least one of the following areas: \nModel serving frameworks (e.g., Triton Inference Server, DeepSpeed Inference, vLLM) \nML runtimes (e.g., ONNX Runtime, TVM, IREE, XLA) \nDeploying ML workloads (LLMs, VLMs, NLP, etc.) across distributed systems \nImplement and optimize ML operators and kernels with a focus on vectorization and efficient execution (e.g., activation, pooling, quantization) \nHardware-aware optimizations and performance tuning \n2+ years of experience developing software targeting AI hardware \nContribution to open-source projects (e.g., LLVM/MLIR, PyTorch, TensorFlow, ONNX Runtime, xDSL, IREE) is a big plus.","description_format":"text","description_chars":2403,"description_truncated":false,"requirements":{"experience_years_min":2,"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":["UI/UX Design","IT Consulting & Digital Transformation","IT Outsourcing & Dedicated Teams","Custom Software Development"],"lifecycle":[{"event":"open","at":"2026-10-11T01:06:20Z"}],"visa":[],"liveness":{"score":16,"band":"cold","label":"Long shot","p_open":1,"p_active":0.453,"p_room":0.36,"age_days":53,"expected_fill_days":29,"reasons":["conf:4","win:tail","crowd:junior"],"computed_at":"2026-10-12T06:55:09Z"},"pay":null,"html_url":"https://alion.io/job/htec-ai-inference-engineer","json_url":"https://alion.io/job/htec-ai-inference-engineer.json","meta":{"generated_at":"2026-10-13T05:47:10Z","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":8911,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-14T00:00:00Z"}},"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":55786},"rest":"https://alion.io/mcp/rest/get_company?id=55786"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fhtec-ai-inference-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%2Fhtec-ai-inference-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%2Fhtec-ai-inference-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/htec-ai-inference-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fhtec-ai-inference-engineer"}]}