{"id":1364724,"url":"https://alion.io/job/lattice-semiconductor-sr-staff-engineer","title":"Sr Staff Engineer","company":{"id":1792396,"name":"Lattice Semiconductor","domain":"latticesemi.com","url":"https://alion.io/company/latticesemi","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","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":"2026-10-03T05:45:00Z"}},"role":"Industrial Engineering","role_family":"Industrial Engineering","seniority":"staff","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Jose, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":129000,"max_usd":249000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":770},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"Claude","optional":false},{"name":"Docker","optional":false},{"name":"GCP","optional":false},{"name":"Gemini","optional":false},{"name":"Knowledge Distillation","optional":false},{"name":"Kubernetes","optional":false},{"name":"LangChain","optional":false},{"name":"Llama","optional":false},{"name":"llama.cpp","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false},{"name":"Mistral","optional":false},{"name":"Model Distillation","optional":false},{"name":"ONNX","optional":false},{"name":"OpenAI","optional":false},{"name":"PyTorch","optional":false},{"name":"Quantization","optional":false},{"name":"RAG","optional":false},{"name":"TensorRT","optional":false},{"name":"vLLM","optional":false}],"status":"live","first_seen_at":"2026-09-24T00:00:00Z","employer_posted_date":"2026-09-24","last_verified_at":"2026-10-03T23:27:34Z","board_verified":true,"closed_at":null,"days_open":10,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":10},"description":"Lattice Overview\nThere is energy here…energy you can feel crackling at any of our international locations. It’s an energy generated by enthusiasm for our work, for our teams, for our results, and for our customers. Lattice is a worldwide community of engineers, designers, and manufacturing operations specialists in partnership with world-class sales, marketing, and support teams, who are developing programmable logic solutions that are changing the industry. Our focus is on R&D, product innovation, and customer service, and to that focus, we bring total commitment and a keenly sharp competitive personality.\nEnergy feeds on energy. If you flourish in a fast paced, results-oriented environment, if you want to achieve individual success within a “team first” organization, and if you believe you can contribute and succeed in a demanding yet collegial atmosphere, then Lattice may well be just what you’re looking for.\nJob Description:\nWe are looking for a Sr. Staff Engineer to join our team.\nKey Responsibilities\nDesign and architect enterprise-wide Generative AI solutions, including reference architectures, integration patterns, and technical standards.\nDesign, build, and maintain an enterprise AI gateway to centralize access, governance, and monitoring of AI model consumption across the organization.\nDevelop and implement intelligent routing techniques to direct requests across multiple large language models (LLMs) and AI providers based on cost, latency, accuracy, and availability requirements.\nEvaluate and integrate local/on-premises models as alternatives to third-party hosted models, with a focus on reducing operational costs.\nEstablish frameworks for measuring and demonstrating cost savings achieved through model selection, routing optimization, and infrastructure decisions.\nCollaborate with engineering, security, and compliance stakeholders to ensure AI architecture adheres to organizational governance and regulatory requirements.\nDefine best practices for prompt orchestration, caching strategies, and fallback mechanisms within the AI gateway.\nProvide technical leadership and mentorship to engineering teams adopting Generative AI capabilities.\nProvide mentorship and lead a team of AI/ML engineers.\nRequired Qualifications\nDemonstrated experience architecting Generative AI solutions at an enterprise scale.\nResearch and integrate cutting-edge LLMs and autonomous AI agent architecture into development processes\nDevelop RAG pipelines that enhance AI‘s ability to retrieve relevant knowledge and generate context-aware responses.\nBuild and optimize agentic AI systems that can interact with APIs, databases, and development environments (such as LangChain, OpenAI APIs, etc.)\nFine-tune LLMs (GPT, Llama, Mistral, Claude, Gemini etc.) for domain-specific applications.\nOptimize models for local inference through quantization, pruning, and distillation.\nDeploy models on-prem or at the edge using frameworks such as PyTorch, TensorRT, ONNX, vLLM, or llama.cpp.\nBuild and maintain training and inference pipelines for reproducibility and scalability.\nIntegrate locally deployed models into production systems via APIs and internal services.\nMonitor model performance, drift, latency, and resource utilization in production\nOptimize retrieval mechanisms to enhance response accuracy, grounding AI outputs in real-world data \nHands-on experience designing and implementing AI gateway solutions and model routing techniques. \nProven track record of achieving measurable cost savings through the use of local/open-source models or alternative optimization techniques. \nStrong understanding of LLM provider ecosystems, API integration patterns, and multi-model orchestration. \nExperience with cloud infrastructure and enterprise architecture frameworks. \nSolid grasp of AI governance, security, and compliance considerations in enterprise environments. \nExcellent communication skills, with the ability to present technical concepts to both technical and non-technical stakeholders. \nArchitect and deploy scalable AI models and retrieval pipelines using cloud-based MLOps pipelines (AWS/GCP/Azure, Docker, Kubernetes)\nOptimize LLMs for real-time AI inferencing, ensuring low latency and high-performance AI solutions \nEducation: Master's or Ph.D. in Computer Science, AI, Machine Learning, or a related field.\nExperience: 5+ years of experience in AI and machine learning, with at least 2 years of experience working on LLMs, code generation, RAG, or AI-powered automation\nPay & Benefits\nConsistent with Lattice Semiconductor values and applicable law, we provide the following information to promote pay transparency and equity. We have a market-based pay structure which varies by location. Please note that the base pay range is a guideline, and our compensation range reflects the cost of labor in the U.S. geographic market based on the location of the role. Pay within these ranges varies and depends on job-related knowledge, skills, and relevant work experience.\nFor candidates who receive and offer, the starting salary will vary based on various factors including, but not limited to, such qualifications as, skill level, competencies, and work location. The range provided may represent a candidate range and may not reflect the full range for an individual tenured employee.\nBase Pay Range\n220800In addition to base pay, this role may be eligible for variable/ incentive compensation and/ or equity. In addition, this role is eligible for a comprehensive, competitive benefits package which may include healthcare and retirement plans, paid time off, and more!\nAdditional Information:\nThis position requires a successful background and reference checks and satisfactory proof of your right to work in the United States.\nLattice recognizes that employees are its greatest asset and the driving force behind success in a highly competitive, global industry. Lattice continually strives to provide a comprehensive compensation and benefits program to attract, retain, motivate, reward and celebrate the highest caliber employees in the industry.\nLattice is an international, service-driven developer of innovative low cost, low power programmable design solutions. Our global workforce, some 1,000 strong, shares a total commitment to customer success and an unbending will to win. For more information about how our FPGA, CPLD and programmable power management devices help our customers unlock their innovation, visit www.latticesemi.com. You can also follow us via Twitter, Facebook, or RSS. At Lattice, we value the diversity of individuals, ideas, perspectives, insights and values, and what they bring to the workplace. Applications are welcome from all qualified candidates.\nAs an E-Verify employer, we use this system to confirm the employment eligibility of all new hires in accordance with federal law. All applicants will be required to complete a Form I-9, Employment Eligibility Verification, upon hire. We do not use E-Verify to pre-screen job candidates and will comply with all E-Verify regulations.","description_format":"text","description_chars":7056,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":false},"security_clearance":false,"languages":[]},"benefits":["Equity","Retirement plans"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Hardware","Smart City"],"lifecycle":[{"event":"open","at":"2026-09-28T01:41:50Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 6 · green card filings: 5","filings_12m":6,"filings_prev_12m":9,"green_card_filings_12m":5,"median_offered_wage_usd":174318,"route":null,"cap_exempt":false,"checked_at":"2026-10-03T21:08:04+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)","US Department of Labor: PERM disclosure data (green cards)"],"filings_for_role_12m":0}],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":9,"expected_fill_days":53,"reasons":["conf:0","velocity","win:early","comp:brand"],"computed_at":"2026-10-03T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/lattice-semiconductor-sr-staff-engineer","json_url":"https://alion.io/job/lattice-semiconductor-sr-staff-engineer.json","meta":{"generated_at":"2026-10-04T00:27:06Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":464,"day_limit":5000,"remaining_today":4536,"minute_limit":60,"resets_at":"2026-10-05T00:00:00Z"}}}