{"id":2702650,"url":"https://alion.io/job/knightec-group-thesis-context-engineering-for-autonomous-software-development-bridging-the-model-capability-gap","title":"Thesis: Context Engineering for Autonomous Software Development: Bridging the Model Capability Gap","company":{"id":678206,"name":"Knightec Group","domain":"knightecgroup.com","url":"https://alion.io/company/knightecgroup","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Teamtailor","truth_index":{"grade":"C","score":57,"open_postings":26,"ghost_share":0.423,"stale_share":0.077,"repost_share":0.731,"time_to_fill_p50_days":80,"computed_at":"2026-10-20T05:45:00Z"}},"role":"Backend","role_family":"Backend","seniority":null,"employment_type":"internship","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Sundsvall, Sweden"],"countries":["SE"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":53000,"max_usd":136000,"period":"year","method":"role_country_seniority_unknown","sample_n":20},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Anthropic","optional":false},{"name":"Context Engineering","optional":false},{"name":"Fine-tuning","optional":false},{"name":"GDPR","optional":false}],"status":"live","first_seen_at":"2026-10-14T14:15:16Z","employer_posted_date":"2026-10-14","last_verified_at":"2026-10-20T12:01:58Z","board_verified":true,"closed_at":null,"days_open":6,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":6},"description":"High Level Description\n Autonomous AI coding agents increasingly rely on powerful frontier language models to understand and modify complex software systems. However, these models can be expensive to operate, while smaller and more affordable models often struggle with the same development tasks.\nContext engineering offers a potential way to narrow this gap by systematically selecting, structuring, and supplying relevant information about the codebase, architecture, development conventions, and task at hand.\nThis thesis investigates whether well-engineered context can enable smaller or less capable language models to approach the performance of frontier models on realistic software development tasks. It also explores how much context is actually needed, and whether providing too much information can reduce performance rather than improve it.\nProject Description\n In this thesis, investigate and build a reusable context engineering pipeline for autonomous AI coding agents. The pipeline should support different strategies for selecting, structuring, and supplying context to language models working on software development tasks within an existing codebase.\nThree context engineering approaches should be compared:\nPersistent project context:Human-authored documentation, architecture descriptions, coding guidelines, and project instructions that remain available across tasks.\nTask-specific manual context:Relevant code, dependencies, and architectural information selected and prepared by a human for a particular development task.\nAutomatically generated context:Relevant information identified and assembled automatically through repository analysis, code search, retrieval, or summarization.\nThese approaches should be evaluated against a baseline coding agent operating without additional prepared context, while retaining its normal ability to explore the repository and use development tools.\nThe evaluation should compare smaller and frontier language models performing the same tasks in representative industrial-style software repositories. The solution should be model-agnostic, supporting both local and cloud-based inference. Local execution of smaller models is optional, not a requirement.\nThe prototype should preferably be built on an existing autonomous coding agent harness, such as OpenCode, rather than requiring a new agent framework.\nParticular attention should be given to context quantity and relevance. By systematically varying the amount of useful information and introducing redundant or unrelated context, investigate when additional context stops improving performance or begins to negatively affect the agent's results.\nThe evaluation should use reproducible development tasks, such as feature implementation, bug fixing, and refactoring, with automated tests and clearly defined success criteria. It should also distinguish between context prepared before task execution and information the agent discovers independently through repository exploration.\n\nWho are we looking for?\nMaster of Science students in Computer Science, Software Engineering, or related fields.\n\nGraduation in June 2027\n\nFluency in Swedish, both written and spoken\n\nFluency in English, both written and spoken \n\nPurpose\nI n this thesis, investigate these questions:\nCan context engineering compensate for lower model capability?\n\nHow much can engineered context reduce the performance gap between smaller language models and frontier models?\n\nFor which types of software development tasks is context engineering most effective?\n\nWhich context engineering strategies work best?\n\nHow do persistent project documentation, manually curated task-specific context, and automatically generated context compare?\n\nDoes their effectiveness differ depending on model capability?\n\nTo what extent does prepared context reduce the need for independent repository exploration?\n\nHow much context is enough?\n\nHow does the amount of relevant context influence task completion performance?\n\nAt what point does additional context provide diminishing returns?\n\nCan excessive, redundant, or irrelevant context negatively affect performance, particularly for smaller models?\n\nWhat are the practical trade-offs?\n\nHow do different context strategies affect task success, execution time, inference cost, and context preparation effort?\n\nCan smaller models with engineered context provide a more cost-effective alternative to frontier models?\n\nHow complex is it to implement and maintain a reusable context engineering pipeline?\n\nThe primary evaluation should measure functional task success and the reduction in the performance gap between smaller and frontier models, without requiring a predefined equivalence threshold.\nExperiments should use consistent agent tooling, reproducible repository states, and comparable execution conditions.\nOut of scope:Training or fine-tuning language models, developing a new autonomous coding agent framework, extensive hardware benchmarking, optimizing local inference infrastructure, and establishing universally optimal context configurations across all software development environments.\nReferences\nOpenCode - https://opencode.ai/\n\nSWE-bench - https://www.swebench.com/\n\nAnthropic, Effective Context Engineering for AI Agents - https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents\n\nAn Exciting Journey with Knightec Group\n Semcon and Knightec have joined forces as Knightec Group. Together, we are Northern Europe’s leading strategic partner in product and digital service development. With a unique combination of cross-functional expertise and a holistic business understanding, we help our clients realize their strategies - from idea to complete solution.\n\nPractical Information\nThis is a thesis position, located at our office in Sundsvall. Start date January or March 2027.\nPlease submit your application as soon as possible, but no later than 2026-11-30. If you have any questions, you are welcome to contact . Note that due to GDPR, we only accept applications through our careers page.","description_format":"text","description_chars":6085,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":false},"security_clearance":false,"languages":[{"language":"Swedish","level":"Advanced (C1)","optional":false},{"language":"English","level":"Advanced (C1)","optional":false}]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Consulting & Digital Transformation","Engineering Services"],"lifecycle":[{"event":"open","at":"2026-10-16T11:38:05Z"}],"visa":[],"liveness":{"score":63,"band":"ok","label":"Likely open","p_open":1,"p_active":0.632,"p_room":1,"age_days":5,"expected_fill_days":80,"reasons":["conf:3","stale_co","velocity","win:early"],"computed_at":"2026-10-20T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/knightec-group-thesis-context-engineering-for-autonomous-software-development-bridging-the-model-capability-gap","json_url":"https://alion.io/job/knightec-group-thesis-context-engineering-for-autonomous-software-development-bridging-the-model-capability-gap.json","meta":{"generated_at":"2026-10-20T14:49:55Z","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":16648,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-21T00:00:00Z"}},"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":678206},"rest":"https://alion.io/mcp/rest/get_company?id=678206"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fknightec-group-thesis-context-engineering-for-autonomous-software-development-bridging-the-model-capability-gap"},{"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%2Fknightec-group-thesis-context-engineering-for-autonomous-software-development-bridging-the-model-capability-gap"},{"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%2Fknightec-group-thesis-context-engineering-for-autonomous-software-development-bridging-the-model-capability-gap"},{"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/knightec-group-thesis-context-engineering-for-autonomous-software-development-bridging-the-model-capability-gap\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fknightec-group-thesis-context-engineering-for-autonomous-software-development-bridging-the-model-capability-gap"}]}